mcp-builder
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [EXTERNAL_DOWNLOADS] (INFO): The skill instructs the agent to fetch documentation from 'modelcontextprotocol.io' and 'github.com/modelcontextprotocol'. These are trusted sources for the protocol, and the content requested consists of text or markdown documentation, not executable scripts.- [PROMPT_INJECTION] (SAFE): No instructions designed to override the agent's behavior or bypass safety constraints were detected.- [DATA_EXFILTRATION] (SAFE): No patterns involving access to sensitive local files or unauthorized data transmission to external domains were found.- [REMOTE_CODE_EXECUTION] (SAFE): The skill does not contain instructions to download and execute remote code or scripts.
Audit Metadata